Joint RNN transducer for ASR and speaker diarization reduces word-level diarization error rate from 15.8% to 2.2% on medical conversations.
Joint Speech Recognition and Speaker Diarization via Sequence Transduction
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems, namely, an automatic speech recognition (ASR) system and a speaker diarization (SD) system. The two systems are trained independently with different objective functions. Often the SD systems operate directly on the acoustics and are not constrained to respect word boundaries and this deficiency is overcome in an ad hoc manner. Motivated by recent advances in sequence to sequence learning, we propose a novel approach to tackle the two tasks by a joint ASR and SD system using a recurrent neural network transducer. Our approach utilizes both linguistic and acoustic cues to infer speaker roles, as opposed to typical SD systems, which only use acoustic cues. We evaluated the performance of our approach on a large corpus of medical conversations between physicians and patients. Compared to a competitive conventional baseline, our approach improves word-level diarization error rate from 15.8% to 2.2%.
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Joint Speech Recognition and Speaker Diarization via Sequence Transduction
Joint RNN transducer for ASR and speaker diarization reduces word-level diarization error rate from 15.8% to 2.2% on medical conversations.